NN
SHENGJINGWANGLUO
WaPyAu
这个作者很懒,什么都没留下…
展开
-
Regularization
RegularizationDeep Learning models have so much flexibility and capacity that overfitting can be a serious problem, if the training dataset is not big enough. Sure it does well on the training set, b...原创 2020-04-17 15:00:37 · 281 阅读 · 0 评论 -
initialization methods 参数初始化
1 - Neural Network modelYou will use a 3-layer neural network (already implemented for you). Here are the initialization methods you will experiment with:Zeros initialization – setting initializatio...原创 2020-04-16 21:16:02 · 729 阅读 · 0 评论 -
pytorch loss function 总结
19 种损失函数tensorflow和pytorch很多都是相似的,这里以pytorch为例1、 L1范数损失 L1Loss计算 output 和 target 之差的绝对值。torch.nn.L1Loss(reduction=‘mean’)参数:reduction-三个值,none: 不使用约简;mean:返回loss和的平均值;sum:返回loss的和。默认:mean。2、均方误...转载 2020-04-16 20:10:55 · 529 阅读 · 0 评论